检索结果-内蒙古大学图书馆

Efficient Joint Deployment of Multi-UAVs for Target Tracking 19th

Efficient Joint Deployment of Multi-UAVs for Target Tracki...

19th EAI International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness, QShine 2023

作者： Wang, Jiashuai Sun, Lu Wan, Liangtian Zheng, Jibin Wang, Xianpeng Institute of Information Science Technology Dalian Maritime University Dalian China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China National Laboratory of Radar Signal Processing Xidian University Xian China State Key Laboratory of Marine Resource Utilization in South China Sea and College of Information Science and Technology Hainan University Haikou China

ISBN: (纸本)9783031651229

Target tracking plays an important role in many real-world applications, such as in vegetation protection, disaster rescue, wildlife observation, etc. Multiple unmanned aerial vehicles (multi-UAVs) can provide effective services for target tracking through efficient joint deployment satisfying the system constraints. The constraints include the energy and no-fly zone constraint of each UAV, the communication distance and safe distance among multi-UAVs, the number of UAVs. As there exists no ready-made model that considers all the above constraints, meanwhile, the energy and no-fly zone restrict the deployment of multi-UAVs for target tracking. In this paper, we propose a model which considers no-fly zone and the energy constraint simultaneously for the joint deployment of multi-UAVs. The objective function is defined as minimizing the distance of each UAV and the threats of target so that it can deploy multi-UAVs reasonably. Second, we propose an improved Nondominated Sort Genetic Algorithm II (NSGAII) with new encoding and decoding mechanisms and the no-fly zone avoidance strategy which can improve the searching performance of joint deployment of multi-UAVs. Finally, we design a set of experiments and the experimental results demonstrate that our proposed algorithm can deploy multi-UAVs for target tracking efficiently compared with the state-of-the-arts methods. © ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Cascaded mixed pyramid pooling for surface defect segmentation in solid oxide fuel cell 3

Cascaded mixed pyramid pooling for surface defect segmentati...

引用

3rd International Conference on Electronic information Engineering, Big Data, and Computer technology, EIBDCT 2024

作者： Wang, Yaokun Fu, Xiaowei Li, Xi Xu, Wei College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Hubei Wuhan430065 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

ISBN: (纸本)9781510680449

To address the issues of defect leakage and mis-segmentation in the surface defect segmentation of solid oxide fuel cells, we propose a cascaded mixed pyramid pooling segmentation method. In the encoding part, attention-based depth-wise separable convolution is implemented to replace the traditional convolution. This reduces the computational complexity and achieves hierarchical feature extraction. Secondly, cascaded sampling is applied to the last three layers of the encoder to promote multi-level feature fusion, and mixed pyramid pooling consisting of atrous convolution and strip pooling is adopted to achieve feature extraction for long-range band defects. Lastly, an adaptive loss function is constructed to supervise the training process, balancing the relative importance among the losses and improving the learning of defect features by the network. The experiments demonstrate that the proposed method improves segmentation accuracy, as evidenced by better results in mean absolute error, F1 score, intersection over union, and Pratt's figure of merit. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Perspective on Rhythmic Gymnastics Performance Analysis Powered by Intelligent Fabric

引用

Advanced Fiber Materials 2023年第1期5卷 1-11页

作者： Dan Zhu Zhenyu Zhang Min Chen Pan Li Yuanzhuo Xiang Jingyu Ouyang Zhiheng Huang Xiaojuan Liu Fuhong Wang Maiping Yang Hongtao Zeng Ping Hong Lei Wei Chong Hou Guangming Tao School of Martial Arts and Performance Capital University of Physical Education and SportsBeijing 100191China Wuhan National Laboratory for Optoelectronics and School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China State Key Laboratory of Material Processing and Die&Mould Technology School of Materials Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China School of Sports Medicine and Mealth Chengdu Sport UniversityChengdu 610000China School of Physical Education Chaohu UniversityHefei 238000China School of Physical Education Huazhong University of Science and TechnologyWuhan 430074China Beijing Sport University Beijing 100091China School of Electronic and Electrical Engineering and School of Materials Science and Engineering Nanyang University of TechnologySingapore 639798Singapore School of Optics and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China

Performance analysis is an important tool for gymnasts and coaches to assess the techniques,strengths,and weaknesses of rhythmic gymnasts during *** have an accurate insight about the motion and postures can help the optimization of their performance and offer personalized ***,there are three primary limitations of traditional perfor-mance analysis systems applied in rhythmic gymnastics:(1)Inability to quantify anthropometric data in an imperceptible way,(2)labor-intensive nature of data labeling and analysis,and(3)lack of monitoring of all-round and multi-dimensional perspectives of the ***,an advanced performance analysis system for rhythmic gymnastics is proposed in this paper,powered by intelligent *** system uses intelligent fabric to detect the physiological and anthropometric data of the *** a variety of data are collected,the analysis component is implemented by artificial intelligence techniques resulting in behavior recognition,decision-making,and other functions assisting performance improvement.A feasible solution to implementing the analysis component is the use of the hyperdimensional computing *** addition,four typical applications are presented to improve training *** by intelligent fabric,the proposed advanced performance analysis system exhibits the potential to promote innovative technologies for improving training and competi-tive performance,prolonging athletic careers,as well as reducing sports injuries.

关键词： Rhythmic gymnastics Intelligent fabric Augmented reality Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Molten salt synthesis of porous carbon and its application in supercapacitors: A review

引用

Journal of Energy Chemistry 2021年第10期30卷 622-640,I0016页

作者： Zhongya Pang Guangshi Li Xiaolu Xiong Li Ji Qian Xu Xingli Zou Xionggang Lu State Key Laboratory of Advanced Special Steel&Shanghai Key Laboratory of Advanced Ferrometallurgy&School of Materials Science and Engineering Shanghai University99#Shangda RoadShanghai 200444China State Key Laboratory of ASIC and System School of MicroelectronicsFudan University825#Zhangheng RoadShanghai 200433China

Carbon materials have taken an important role in supercapacitor applications due to their outstanding features of large surface area,low price,and stable physicochemical *** research efforts have been devoted to the development of novel synthesis strategy for the preparation of porous carbon materials in recent *** particular,molten salt strategy represents an emerging and promising method,whereby it has shown great potential in achieving tailored production of porous *** has been proved that the molten salt-assisted production of carbon via the direct carbonization of carbonaceous precursors is an effective ***,with the incorporation of electrochemical technology,molten salt synthesis of porous carbon has become flexible and ***,this review focuses on the mainstream molten salt synthesis strategies for the production of porous carbon materials,which includes direct molten salt carbonization process,capture and electrochemical conversion of CO_(2)to value-added carbon,electrochemical exfoliation of graphite to graphene-based materials,and electrochemical etching of carbides to new-type carbide-derived carbon *** reaction mechanisms and recent advances for these strategies are reviewed and discussed *** morphological and structural properties and capacitive performances of the obtained carbon materials are summarized to reveal their appealing points for supercapacitor ***,the opportunities and challenges of the molten salt synthesis strategy for the preparation of carbon materials are also discussed in this review to provide inspiration to the future researches.

关键词： Molten salt synthesis Porous carbon CO_(2)conversion Graphene Carbide-derived carbon

来源：评论

学校读者我要写书评

暂无评论

Ultra-fast, high-power MUTC Photodiodes with bandwidth-efficiency product over 130 GHz × 100%

arXiv

引用

arXiv 2025年

作者： Li, Linze Long, Tianyu Yang, Xiongwei Zhang, Zhouze Wang, Luyu Wang, Jingyi Wang, Mingxu Lu, Juanjuan Yu, Jianjun Chen, Baile School of Information Science and Technology ShanghaiTech University Shanghai201210 China Fastphide Photonics Shanghai201210 China China State Key Laboratory of ASIC and System Fudan University Shanghai200433 China Key Laboratory for Information Science of Electromagnetic Waves Shanghai Institute for Advanced Communication and Data Science Fudan University Shanghai200433 China School of Information Science and Technology Fudan University Shanghai200433 China

The accelerating demand for wireless communication necessitates wideband, energy-efficient photonic sub-terahertz (sub- THz) sources to enable ultra-fast data transfer. However, as critical components for THz photonic mixing, photodiodes (PDs) face a fundamental trade-off between quantum efficiency and bandwidth, presenting a major obstacle to achieving high-speed performance with high optoelectronic conversion efficiency. Here, we overcome this challenge by demonstrating an InP-based, waveguide-integrated modified unitraveling carrier photodiode (MUTC-PD) with a terahertz bandwidth exceeding 200 GHz and a bandwidth-efficiency product (BEP) surpassing 130 GHz × 100%. Through the integration of a spot-size converter (SSC) to enhance external responsivity, alongside optimized electric field distribution, balanced carrier transport, and minimized parasitic capacitance, the device achieves a 3-dB bandwidth of 206 GHz and an external responsivity of 0.8 A/W, setting a new benchmark for BEP. Packaged with WR-5.1 waveguide output, it delivers radiofrequency (RF) power exceeding -5 dBm across the 127-185 GHz frequency range. As a proof of concept, we achieved a wireless transmission of 54 meters with a single-line rate of up to 120 Gbps, leveraging photonics-aided technology without requiring a low-noise amplifier (LNA). This work establishes a pathway to significantly enhance optical power budgets and reduce energy consumption, presenting a transformative step toward high-bandwidth, high-efficiency sub-THz communication systems and next-generation wireless networks. Copyright © 2025, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Accurate capacitance-voltage characterization of organic thin films with current injection

引用

Chinese Physics B 2021年第8期30卷 462-468页

作者： Ming Chu Shao-Bo Liu An-Ran Yu Hao-Miao Yu Jia-Jun Qin Rui-Chen Yi Yuan Pei Chun-Qin Zhu Guang-Rui Zhu Qi Zeng Xiao-Yuan Hou State Key Laboratory of Surface Physics Fudan UniversityShanghai 200433China State Key Laboratory of ASIC and System Center of Micro-Nano SystemSISTFudan UniversityShanghai 200433China Key Laboratory of Luminescence and Optical Information Ministry of EducationSchool of ScienceBeijing Jiaotong UniversityBeijing 100044China Department of Physics Chemistry and Biology(IFM)Linköping UniversityLinköping SE-58183Sweden School of Material Engineering Shanghai University of Engineering ScienceShanghai 201620China

To deal with the invalidation of commonly employed series model and parallel model in capacitance-voltage(C-V)characterization of organic thin films when current injection is significant,a three-element equivalent circuit model is *** this basis,the expression of real capacitance in consideration of current injection is theoretically derived by small-signal analysis *** validity of the proposed equivalent circuit and theoretical expression are verified by a simulating circuit consisting of a capacitor,a diode,and a ***,the accurate C-V characteristic of an organic thin film device is obtained via theoretical correction of the experimental measuring result,and the real capacitance is 35.7%higher than the directly measured capacitance at 5-V bias in the parallel *** work strongly demonstrates the necessity to consider current injection in C-V measurement and provides a strategy for accurate C-V characterization experimentally.

关键词： current injection organic thin film capacitance-voltage parasitic resistance

来源：评论

学校读者我要写书评

暂无评论

MFGB: Molecular Properties Prediction leveraging Self-supervised Morgan Fingerprint Representation Learning

MFGB: Molecular Properties Prediction leveraging Self-superv...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Fang, Shuyan Liu, Yu Liu, Song Wuhan University of Science and Technology School of Computer Science and Technology Wuhan China Wuhan University of Science and Technology Hubei Prov. Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China Wuhan University of Science and Technology Hubei Provincial Key Laboratory of Occupational Hazard Identification and Control Hubei Province Wuhan China

ISBN: (纸本)9798350337488

Simple molecular graphs or molecular line notations are insufficient for molecular representation learning models that automatically learn molecule representations to acquire deep semantic features about chemistry. Therefore, we proposed the Morgan Fingerprint Graph, a novel molecular graph model constructed with the nodes of the Morgan Fingerprint Identifier, whose nodes incorporate various properties of the atom neighborhood. Based on our Morgan Fingerprint Graph, we trained a BERT-based molecular representation model MFGB which employs a local rather than global attention module to adapt the model to the Morgan Fingerprint Graph. The attention module of MFGB regulates the exchange of information in the attention layer based on the connection information of the atoms in the molecules. To verify the effectiveness of MFGB, we selected several mainstream datasets for evaluation. The results demonstrated that our method improve the performance of molecular properties prediction. In addition, we analyzed MFGB from both the over-smoothing and the attention perspectives. The analysis indicates that the node vector representations learned from the Morgan Fingerprint Graph are generally less smoothing, and the attention distributions of MFGB match the partial charge density distribution of the molecules. © 2023 IEEE.

关键词： Molecular property prediction Molecular representation learning Morgan Fingerprint Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A UAV-Based Remote Sensing Image Automatic Monitoring system Empowered by Artificial Intelligence

A UAV-Based Remote Sensing Image Automatic Monitoring System...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence systems, IACIS 2024

作者： Liu, Tao Zhang, Bohan College of Computer Science and Technology Heilongjiang Institute of Technology Harbin China School of Information Engineering China University of Geosciences Wuhan Wuhan China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China

ISBN: (纸本)9798350360660

In this study, an automatic monitoring system based on convolutional neural network (CNN) is proposed to address the automation and accuracy of remote sensing image processing. With the maturity and wide application of remote sensing and UAV technologies, efficient and accurate image analysis methods have become particularly important. We developed this system through in-depth research on multiple stages of data preprocessing, feature extraction and model training. In the experimental stage, through the comparison experiments with Support Vector Machine (SVM) and Random Forest (RF) models, it is found that the CNN model has significant advantages in processing speed, anti-interference ability and accuracy. Especially in the processing of urban remote sensing images, CNN exhibits up to 90% accuracy, showing its wide applicability and excellent cross-domain application capability. Overall, this study not only successfully develops an efficient and accurate automatic monitoring system for remote sensing images, but also provides strong theoretical and experimental support for future optimization of CNN architecture in natural environments, improvement of real-time data processing capability, and extension to practical applications such as disaster monitoring and environmental protection. © 2024 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

LDACS-Based Wide Area Multilateration for Surveillance: An Iterative Reweighted Least Square Method Using TDOA and FDOA Measurements

LDACS-Based Wide Area Multilateration for Surveillance: An I...

引用

2025 Integrated Communications, Navigation and Surveillance Conference, ICNS 2025

作者： Geng, Jiayi Bai, Tong Du, Wanlin Xiong, Yifeng Wang, Zhipeng School of Cyber Science and Technology Beihang University State Key Laboratory of CNS/ATM Beijing100191 China School of Electronic and Information Engineering Beihang University State Key Laboratory of CNS/ATM Beijing100191 China Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9798331534738

The L-band Digital Aeronautical Communication system (LDACS) has been recognized by the International Civil Aviation Organization (ICAO) as the first integrated communication, navigation, and surveillance system designed for future air traffic management. In wide-area multipoint wireless positioning, recent studies have investigated various techniques, including those based on Time Difference of Arrival (TDOA). However, conventional methods are often limited by low estimation accuracy and slow convergence, mainly when applied to fast-moving targets such as aircraft. To address these challenges, this study proposes a hybrid TDOA and Frequency Difference of Arrival (FDOA) method designed to improve the accuracy of position and velocity estimation for aircraft using LDACS ground stations. To overcome the limitations of traditional methods, the proposed approach incorporates the Iterative Weighted Least Squares (IRLS) method, which refines the iterative process and improves the precision of the estimation. To validate the effectiveness of the technique, the Cramér-Rao Lower Bound (CRLB) is derived, and a series of simulation experiments are conducted to assess performance. The results demonstrate that the proposed method achieves high accuracy and computational efficiency, approaching CRLB performance, thus reinforcing the feasibility of LDACS for aircraft surveillance applications. © 2025 IEEE.

关键词： Cramer-Rao bounds

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Active Power Dispatch for Wind Farms 13

Data-Driven Active Power Dispatch for Wind Farms

引用

13th IEEE Data Driven Control and Learning systems Conference, DDCLS 2024

作者： Jiao, Xuguo Zhang, Daoyuan Wang, Xin Ma, Zhaoxing Zhang, Zhenyong Liu, Wenfeng School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China College of Computer Science and Technology Guizhou University State Key Laboratory of Public Big Data Guiyang550025 China School of Civil Engineering Qingdao University of Technology Qingdao266520 China

ISBN: (纸本)9798350361674

Active power dispatch of wind farms plays an important role in power grid scheduling. In this paper, a data-driven active power dispatch strategy for wind farms is proposed, which uses the key point of minimizing the standard deviation of wind turbines' output power series to reduce their fluctuations. First, to build the optimization problem, the historical active power output data of each wind turbine is collected from the Supervisory Control And Data Acquisition (SCADA) system. Then, the objective function is developed based on the idea of minimizing the standard deviation of the output power time series. Meanwhile, considering the constraints of wind turbines' output power and active power balance of the grid, the feasible domain of the cost function is constructed. Further, to solve the proposed nonlinear optimization problem with equality and inequality constraints, the trust region interior point method (TRIPM) is employed to explore optimal solution within the feasible domain. Finally, actual data collected from wind farms is used to test effectiveness of the designed approach and experimental results show that our method can achieve better output power smoothing performance than conventional Proportional Dispatch (PD) method. © 2024 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：